Patent · US Active

Efficiency adjustable speech recognition system

US11715462B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 29, 2021
Grant dateAug 1, 2023
Priority date
Expiry dateJan 13, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/22
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computing system is configured to generate a transformer-transducer-based deep neural network. The transformer-transducer-based deep neural network comprises a transformer encoder network and a transducer predictor network. The transformer encoder network has a plurality of layers, each of which includes a multi-head attention network sublayer and a feed-forward network sublayer. The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using the transformer-transducer-based deep neural network. The E2E ASR model has one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.